The paper introduces TRON, an online, rule-verifiable environment substrate that generates an unbounded stream of fresh, controllable visual reasoning training instances, significantly improving RL pe…

This paper proposes VeriEvol, a framework for scaling reinforcement learning for visual mathematical reasoning by decoupling prompt difficulty and answer reliability, and verifying data construction.

The paper introduces a new benchmark, E2V-Bench, to evaluate text-to-image models on generating pedagogically accurate visuals from arithmetic equations, finding that current models often fail due to…

The paper proposes using Vision-Language Models (VLMs) as 'teachers' to guide Video Generation Models (VGMs) during test-time optimization, significantly improving video reasoning capabilities.

The paper introduces MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal Language Models with an executable mechanism for mental visualization using SVG graphics.

This paper proposes Perceive-to-Reason (P2R), a framework for fine-grained visual reasoning that decouples perception from reasoning and introduces a new reinforcement learning strategy.

The paper introduces APEIRIA, a neuro-symbolic 3D Multi-modal LLM that bridges the gap between interpretable symbolic reasoning and flexible, open-vocabulary 3D understanding.

DenseSteer is a training-free inference-time framework that improves the math reasoning capabilities of small language models by steering their internal representations toward a 'Dense Reasoning' patt…

The paper proposes CSMR, a cognitive scheduling framework that allows a language model to dynamically decide when to acquire task-relevant visual evidence, significantly improving multimodal reasoning…

PlanarBench introduces a novel benchmark to test LLM spatial reasoning by requiring them to draw planar graphs as ASCII art from an edge list, finding that edge count is a stronger difficulty predicto…

The paper deconstructs latent visual reasoning tokens into components and finds that the performance gains are primarily due to boundary markers and attention patterns, not the tokens' ability to enco…

This paper introduces a new evaluation framework, SpatialUncertain, demonstrating that current Vision-Language Models (VLMs) are prone to overconfident and incorrect answers to spatial questions when…

The paper introduces StemBind, a diagnostic benchmark that separates perception, rule induction, and answer selection in abstract visual reasoning, revealing that the primary failure point for MLLMs i…

The authors conducted a user study to assess the effectiveness of their interactive visual query tracer and builder tools for Nemo, a Datalog reasoner, in helping students learn Datalog.

The paper proposes Astra, an agentic framework that equips Vision-Language Models (VLMs) with the ability to perform spatial reasoning by actively generating and utilizing imagined visual evidence fro…

AXIOM is a trust-first neuro-symbolic execution architecture that ensures verifiable mathematical reasoning by strictly separating language model interpretation from deterministic computation, achievi…

This paper proposes SpatialClaw, a training-free framework for spatial reasoning that enables open-ended, complex 3D/4D spatial reasoning.